Military Medicine

Real-time prediction of cardiorespiratory deterioration during paediatric critical care transport using interpretable machine learning.

Interhospital transport of critically ill children carries inherent risks, including unexpected respiratory and cardiovascular deterioration. Early warning of impending patient deterioration may allow physicians to intervene and prevent further decline. We developed and evaluated lightweight, explainable machine learning models to forecast adverse physiological events up to 15 minutes in advance u...

EdgeECG: a lightweight edge-oriented network with dual criterion pruning for real-time ECG arrhythmia classification.

Objective.Miniature electrocardiogram (ECG) devices can rapidly and accurately acquire real-time cardiac signals, enabling timely warnings for patients with heart disease. To achieve accurate arrhythmia classification on resource-constrained ECG edge devices, we propose EdgeECG, an ultra-lightweight neural network designed for deployment on low-power microcontrollers.Approach.EdgeECG is first desi...

Explainable attention-based neural network for load forecasting in super smart grids using socioeconomic and power consumption data.

Super Smart Grids (SSG) aim to provide large-scale, multi-zonal electricity access while dynamically balancing supply and demand. However, their imple...

PGCFuse: a U-Net-based progressive gated convmixer network with global context aggregation for infrared-visible image fusion.

Infrared (IR) and visible (VI) image fusion aims to integrate complementary information from heterogeneous modalities to enhance visual perception in ...

HybridTrust: on-device federated learning with crypto-agile security for legacy and quantum-safe medical devices.

The process of migration of IoMT systems in healthcare into post-quantum cryptographic systems is expected to be a gradual one. Here, existing ECC-bas...

Digital Twins as the Implementation Layer of Precision Medicine in Pediatric Neurosurgery.

Pediatric neurosurgery increasingly utilizes precision medicine, but practitioners encounter challenges in translating complex data into individualize...

Current themes of AI in mental health: Actionable evidence and guardrails for mood and anxiety care.

Currently, artificial intelligence (AI) is clinically relevant to mood and anxiety care, but the evidence base is uneven across use cases. This narrat...

Editorial Commentary: Traveling to A New Dimension in Anterior Cruciate Ligament Injury Risk Stratification: Holistic 3-Dimensional Knee Phenotyping via Automated Artificial Intelligence Pipelines.

Morphologic risk stratification for anterior cruciate ligament injury has historically relied upon isolated two-dimensional radiographic parameters (e...

Artificial Intelligence in Peripheral Artery Disease: A Science Advisory From the American Heart Association.

Artificial intelligence shows promise for improving care for peripheral artery disease through earlier detection, improved risk stratification, more t...

Natural Language Processing of Clinical Notes for Cancer Research and Patient Care Prior to Widespread Adoption of Generative AI: Scoping Review.

BACKGROUND: Clinical notes are the most abundant data type within electronic health records; however, their highly unstructured format presents signif...

A systematic review of machine learning techniques for real-time speech and noise classification in hearing aids.

Introduction: Hearing loss significantly impairs speech comprehension in noisy environments, creating major communication challenges for individuals w...

A lifecycle governance and learning health system framework for trustworthy, generalizable, and sustainable human-ai partnership in clinical practice: Lessons from the asthma-guidance and prediction system (A-GPS).

The integration of artificial intelligence (AI) into clinical decision support (CDS) holds promise for proactive, personalized, and precision care. Ho...

Hessian-guided mixed-precision quantization of vision transformers under hardware constraints.

Vision transformers (ViTs) have attracted increasing attention in visual tasks due to their strong global modeling capability. However, compared with ...

Development and external validation of an interpretable early prediction model for acute kidney injury using TabPFN and routine admission data: a retrospective cohort study.

BACKGROUND: Acute kidney injury (AKI) is a common and serious complication among hospitalized patients, and early risk stratification remains challeng...

Artificial Intelligence in Physical, Occupational and Neuro-Rehabilitation: Clinical Effectiveness, Prognostic Performance, and Pre-Implementation Feasibility - A Systematic Review.

BACKGROUND: Global rehabilitation needs far exceed capacity, and artificial intelligence (AI) is proposed to extend access, personalise therapy, and s...

Addressing the Treatment Gap for Pediatric Headache in Underserved Regions.

PURPOSE OF REVIEW: This review explores innovative strategies to address the treatment gap for pediatric headache disorders in underserved regions wor...

Deep convolutional models for robust multi-crop disease recognition in real-world conditions.

Crop diseases significantly reduce agricultural output and are a serious problem, especially in the parts of the world where diagnostic experts are no...

AI-enabled wireless wearable breathing sensor for breathing pattern recognition.

This paper presents an AI-driven multisensor wearable system for real-time breathing pattern recognition by integrating an inertial measurement unit (...

LiteFeatNet: A parameter-efficient and performance-centric deep learning model for multi-ocular disease identification using intermediate feature reduction from fundus images.

Convolutional Neural Networks (CNNs) require a larger amount of input samples and computing resources to learn discriminative features for accurate id...

Reining In Unbridled AI Enthusiasm: Protecting the Integrity of Rehabilitation Science & Clinical Care.

Enthusiasm for artificial intelligence (AI) applications in rehabilitation medicine has accelerated rapidly, from 22 publications in 2015 to 1,449 in ...